Configuration for the Anthropic model provider.
A provider block with kind = "anthropic" configures the Anthropic cloud provider, which serves
Claude models.
| Field | Type | Required | runtime() | Default | Description |
|---|---|---|---|---|---|
kind | anthropic | yes | no | … | Provider kind. |
models | array<string | ModelEntry> | no | no | unset | Models permitted for this provider, with optional model-specific inference settings. |
config | ProviderConfig | no | unset | API credentials and endpoint settings for this provider. | |
params | InferenceParams | no | unset | Default inference settings for requests to this provider. |
When config.api_key is unset, the key is read from the ANTHROPIC_API_KEY environment variable.
The agent fails to start when neither is set.
| Field | Type | Required | runtime() | Default | Description |
|---|---|---|---|---|---|
name | string | yes | no | … | Model identifier. |
params | InferenceParams | no | unset | Model-specific inference parameter overrides. |
| Field | Type | Required | runtime() | Default | Description |
|---|---|---|---|---|---|
api_key | string | no | yes | unset | Anthropic API key. Wrap in secret(runtime(...)) to keep it out of build artifacts. |
base_url | string | no | yes | unset | API base URL. Useful for proxies or private endpoints. |
headers | map<string, HeaderValue> | no | yes | {} | HTTP headers sent with every model request, keyed by header name. Header names are case insensitive. |
A header value is one of:
| Form | Header value |
|---|---|
| a string | The string, unchanged. |
expression("source") | The result of the CEL expression source, evaluated for each model request. |
config {
headers = {
"X-Team" = "platform"
"X-Tenant-Id" = expression("ctx.tenant_id")
}
}For the values an expression can read and how evaluation fails, see Send custom headers.
The params block sets inference parameter defaults for all models under this provider. All fields
are optional and support runtime().
| Field | Type | Required | runtime() | Default | Description |
|---|---|---|---|---|---|
max_tokens | integer | no | yes | unset | Maximum number of tokens to generate. |
temperature | number | no | yes | unset | Controls randomness when selecting the next token; higher values produce more varied output. |
top_p | number | no | yes | unset | Selects tokens from the smallest group whose combined probability reaches this value. |
top_k | integer | no | yes | unset | Limits the next-token choices to the K most likely tokens. |
stop_sequences | array<string> | no | yes | unset | Sequences that stop generation. |
frequency_penalty | number | no | yes | unset | Reduces repetition by penalizing tokens according to how often they have appeared. |
presence_penalty | number | no | yes | unset | Penalizes tokens that have already appeared to reduce repetition. |
seed | integer | no | yes | unset | Seed for deterministic sampling. |
provider_params | object | no | yes | unset | Additional provider-specific inference options, such as extended thinking, sent directly to the API. |
provider "anthropic" {
kind = "anthropic"
models = [
"claude-haiku-4-5",
{
name = "claude-opus-4-7"
params {
max_tokens = 16000
temperature = 0.8
}
}
]
config {
api_key = secret(runtime("ANTHROPIC_API_KEY"))
base_url = runtime("ANTHROPIC_BASE_URL", "https://api.anthropic.com")
}
params {
max_tokens = 4096
temperature = 0.5
}
}In this example, requests to claude-haiku-4-5 use the provider-level defaults
(max_tokens = 4096, temperature = 0.5). Requests to claude-opus-4-7 use its own
model-level params instead (max_tokens = 16000, temperature = 0.8).
Always wrap API keys in secret(runtime(...)). This prevents the key from appearing in build
artifacts and the output of agentc inspect.
© 2026 pogue.dev. All rights reserved.
CC BY 4.0